sparrow-parse 0.2.1__tar.gz → 0.2.3__tar.gz

{sparrow_parse-0.2.1 → sparrow_parse-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.2.1
+Version: 0.2.3
 Summary: Sparrow Parse is a Python package for parsing and extracting information from documents.
 Home-page: https://github.com/katanaml/sparrow/tree/main/sparrow-data/parse
 License: GPL-3.0
@@ -15,13 +15,14 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Software Development
+Requires-Dist: numpy (==1.26.4)
 Requires-Dist: pymupdf4llm (==0.0.5)
 Requires-Dist: rich (>=13.7.1,<14.0.0)
 Requires-Dist: sentence-transformers (==3.0.1)
 Requires-Dist: torch (==2.2.2)
 Requires-Dist: transformers (==4.41.2)
-Requires-Dist: unstructured-inference (==0.7.33)
-Requires-Dist: unstructured[all-docs] (==0.14.5)
+Requires-Dist: unstructured-inference (==0.7.35)
+Requires-Dist: unstructured[all-docs] (==0.14.6)
 Project-URL: Repository, https://github.com/katanaml/sparrow
 Description-Content-Type: text/markdown
 
@@ -63,7 +64,7 @@ Example:
 
 *model_name* - `yolox`
 
-*options* - `['tables', 'html']`
+*options* - `['tables', 'unstructured']`
 
 *local* - `True`
 

{sparrow_parse-0.2.1 → sparrow_parse-0.2.3}/README.md

@@ -36,7 +36,7 @@ Example:
 
 *model_name* - `yolox`
 
-*options* - `['tables', 'html']`
+*options* - `['tables', 'unstructured']`
 
 *local* - `True`
 

{sparrow_parse-0.2.1 → sparrow_parse-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sparrow-parse"
-version = "0.2.1"
+version = "0.2.3"
 description = "Sparrow Parse is a Python package for parsing and extracting information from documents."
 authors = ["Andrej Baranovskij <andrejus.baranovskis@gmail.com>"]
 license = "GPL-3.0"
@@ -22,12 +22,13 @@ include = [
 [tool.poetry.dependencies]
 python = ">=3.9,<3.12"
 torch = {version = "2.2.2", source = "pypi"}
-unstructured = {version = "0.14.5", extras = ["all-docs"]}
-unstructured-inference = "0.7.33"
+unstructured = {version = "0.14.6", extras = ["all-docs"]}
+unstructured-inference = "0.7.35"
 rich = "^13.7.1"
 pymupdf4llm = "0.0.5"
 transformers = "4.41.2"
 sentence-transformers = "3.0.1"
+numpy = "1.26.4"
 
 
 [tool.poetry.scripts]

sparrow_parse-0.2.3/sparrow_parse/__init__.py

@@ -0,0 +1 @@
+__version__ = '0.2.3'

{sparrow_parse-0.2.1 → sparrow_parse-0.2.3}/sparrow_parse/extractor/unstructured_processor.py

@@ -98,7 +98,7 @@ class UnstructuredProcessor(object):
         if options is None:
             content = self.process_json_file(file_path)
 
-        if options and "tables" in options and "html" in options:
+        if options and "tables" in options and "unstructured" in options:
             content = self.process_json_file(file_path, "form")
 
             table_content = self.process_json_file(file_path, "table")
@@ -173,7 +173,7 @@ if __name__ == "__main__":
     #     '/Users/andrejb/infra/shared/katana-git/sparrow/sparrow-ml/llm/data/invoice_1.pdf',
     #     'hi_res',
     #     'yolox',
-    #     ['tables', 'html'],
+    #     ['tables', 'unstructured'],
     #     True,
     #     True)
 

sparrow_parse-0.2.1/sparrow_parse/__init__.py

@@ -1 +0,0 @@
-__version__ = '0.2.1'